A Deep Learning-based Model for Detecting Abnormalities on Brain MR Images for Triaging: Preliminary Results from a
Romane Gauriau1, Bernardo C Bizzo1, Felipe C Kitamura1
1MGH & BWH Center for Clinical Data Science, Ste 1303, Floor 13, 100 Cambridge St, Boston, MA 02114 (R.G., B.C.B., F.B.C.M., K.P.A.); Department of Artificial Intelligence, Diagnósticos da América, São Paulo, Brazil (B.C.B., F.C.K., O.L.J., S.F.F., M.R.T.G., L.M.V., R.C.D., E.L.G.); Head of AI, Diagnósticos da América SA, São Paulo, Brazil (F.C.K.); Department of Radiology, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil (B.C.B., T.A.S., E.L.G.); Department of Radiology, Massachusetts General Hospital, Boston, Mass (B.C.B.); and Department of Radiology, Brigham and Women's Hospital and Harvard Medical School, Harvard University, Boston, Mass (K.P.A.).
Purpose:
To develop a deep learning model for detecting brain abnormalities on MR images.
Materials And Methods:
In this retrospective study, a deep learning approach using T2-weighted fluid-attenuated inversion recovery images was developed to classify brain MRI findings as "likely normal" or "likely abnormal." A convolutional neural network model was trained on a large, heterogeneous dataset collected from two different continents and covering a broad panel of pathologic conditions, including neoplasms, hemorrhages, infarcts, and others. Three datasets were used. Dataset A consisted of 2839 patients, dataset B consisted of 6442 patients, and dataset C consisted of 1489 patients and was only used for testing. Datasets A and B were split into training, validation, and test sets. A total of three models were trained: model A (using only dataset A), model B (using only dataset B), and model A + B (using training datasets from A and B). All three models were tested on subsets from dataset A, dataset B, and dataset C separately. The evaluation was performed by using annotations based on the images, as well as labels based on the radiology reports.
Results:
Model A trained on dataset A from one institution and tested on dataset C from another institution reached an F1 score of 0.72 (95% CI: 0.70, 0.74) and an area under the receiver operating characteristic curve of 0.78 (95% CI: 0.75, 0.80) when compared with findings from the radiology reports.
Conclusion:
The model shows relatively good performance for differentiating between likely normal and likely abnormal brain examination findings by using data from different institutions.Keywords: MR-Imaging, Head/Neck, Computer Applications-General (Informatics), Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms© RSNA, 2021Supplemental material is available for this article.
